© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1399
    Prev
    Next
    INDEX
    Explanations

    in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lius
    -0.10
    è·º
    -0.09
    aho
    -0.09
    å¤ļå±Ĥ次
    -0.08
    å®ŀçĶ¨
    -0.08
    æĤ£çĹħ
    -0.08
    åįģåħŃ
    -0.08
    âĪ
    -0.08
    blend
    -0.08
    主å¸Ń
    -0.08
    POSITIVE LOGITS
    çĥ¦æģ¼
    0.09
    çķĻåľ¨
    0.09
    æľ«ç«¯
    0.09
    _nh
    0.09
    (formatter
    0.09
    俾
    0.09
    çļĦæĥħæĦŁ
    0.09
    asure
    0.09
    èİĺ
    0.09
    忸
    0.09
    Activations Density 0.042%

    No Known Activations